Engineering CultureFeatured
AI Moved the Bottleneck — and this time it landed in product
We ran out of stories. Our AI pipeline moved faster than product could spec new work. The bottleneck didn't disappear when we shifted left — it migrated.
Engineering Culture
Who Trains the Next Senior Engineers?
AI makes seniors faster and juniors easier to skip — right when the industry needs more seniors, not fewer. A pipeline problem, not a productivity story.
AI Agents & Orchestration
Meet ADLC
Introducing the ADLC — the Agent Development Lifecycle. The loop that governs how you calibrate AI agents to produce reliable output.
AI Agents & Orchestration
The AI-Powered Developer
How 15 specialized agents go from ADO story to shipped PR — orchestration, context management, quality gates, and drift detection.
AI Agents & Orchestration
Auto Mode Needs a Referee
Author agents enforce quality structurally — rating AI output, retrying on partial passes, and escalating when something is fundamentally wrong.
Tooling & Workflows
Your Agent's Rules Are Probably Wrong
Without a feedback loop, your agent skills teach stale patterns — or worse, propagate security rules that were never right.
Tooling & Workflows
Stop Loading 4,600 Lines Nobody Asked For
The architecture that cut per-session agent context by 85–89% — without losing a single useful rule.
Tooling & Workflows
The Three Layers of Agent Knowledge
Not all agent context is the same. The difference between skills, instructions, and scripts determines whether your agent stays focused.
AI Agents & Orchestration
Match the Model to the Job
Using the most powerful model for everything isn't a strategy — it's expensive and slow. Here's how to match models to tasks.
AI Agents & Orchestration
Specialists Beat Generalists
A single generalist agent doing everything sounds simpler. It isn't. Here's why specialists produce better output and preserve context at handoffs.
AI Agents & OrchestrationFeatured
Making the Case for QE in the Age of AI
AI isn't replacing QE — it's making the discipline more essential. The judgment behind good testing is exactly what AI can't supply.